Part 1: Factor management

Factors are how categorical data are stored. The values a factor can take on are called levels. It is important to check variable types. What you think are characters may actually be stored numerically. Let’s explore the data frame.

summary(gapminder)

        country        continent        year         lifeExp     
 Afghanistan:  12   Africa  :624   Min.   :1952   Min.   :23.60  
 Albania    :  12   Americas:300   1st Qu.:1966   1st Qu.:48.20  
 Algeria    :  12   Asia    :396   Median :1980   Median :60.71  
 Angola     :  12   Europe  :360   Mean   :1980   Mean   :59.47  
 Argentina  :  12   Oceania : 24   3rd Qu.:1993   3rd Qu.:70.85  
 Australia  :  12                  Max.   :2007   Max.   :82.60  
 (Other)    :1632                                                
      pop              gdpPercap       
 Min.   :6.001e+04   Min.   :   241.2  
 1st Qu.:2.794e+06   1st Qu.:  1202.1  
 Median :7.024e+06   Median :  3531.8  
 Mean   :2.960e+07   Mean   :  7215.3  
 3rd Qu.:1.959e+07   3rd Qu.:  9325.5  
 Max.   :1.319e+09   Max.   :113523.1  
                                       

Before beginning the factor management exercise, let’s get to know the factors in the gapminder data set.

class(gapminder$country)

[1] "factor"

factor

class(gapminder$continent)

[1] "factor"

factor

class(gapminder$year)

[1] "integer"

integer

class(gapminder$lifeExp)

[1] "numeric"

numeric

class(gapminder$pop)

[1] "integer"

integer

class(gapminder$gdpPercap)

[1] "numeric"

numeric

We see that we have two factors in this data set. Let’s see the levels for “country” and “continent” before we begin filtering the data.

nlevels(gapminder$country)

[1] 142

nlevels(gapminder$continent)

[1] 5

levels(gapminder$country)

  [1] "Afghanistan"              "Albania"                 
  [3] "Algeria"                  "Angola"                  
  [5] "Argentina"                "Australia"               
  [7] "Austria"                  "Bahrain"                 
  [9] "Bangladesh"               "Belgium"                 
 [11] "Benin"                    "Bolivia"                 
 [13] "Bosnia and Herzegovina"   "Botswana"                
 [15] "Brazil"                   "Bulgaria"                
 [17] "Burkina Faso"             "Burundi"                 
 [19] "Cambodia"                 "Cameroon"                
 [21] "Canada"                   "Central African Republic"
 [23] "Chad"                     "Chile"                   
 [25] "China"                    "Colombia"                
 [27] "Comoros"                  "Congo, Dem. Rep."        
 [29] "Congo, Rep."              "Costa Rica"              
 [31] "Cote d'Ivoire"            "Croatia"                 
 [33] "Cuba"                     "Czech Republic"          
 [35] "Denmark"                  "Djibouti"                
 [37] "Dominican Republic"       "Ecuador"                 
 [39] "Egypt"                    "El Salvador"             
 [41] "Equatorial Guinea"        "Eritrea"                 
 [43] "Ethiopia"                 "Finland"                 
 [45] "France"                   "Gabon"                   
 [47] "Gambia"                   "Germany"                 
 [49] "Ghana"                    "Greece"                  
 [51] "Guatemala"                "Guinea"                  
 [53] "Guinea-Bissau"            "Haiti"                   
 [55] "Honduras"                 "Hong Kong, China"        
 [57] "Hungary"                  "Iceland"                 
 [59] "India"                    "Indonesia"               
 [61] "Iran"                     "Iraq"                    
 [63] "Ireland"                  "Israel"                  
 [65] "Italy"                    "Jamaica"                 
 [67] "Japan"                    "Jordan"                  
 [69] "Kenya"                    "Korea, Dem. Rep."        
 [71] "Korea, Rep."              "Kuwait"                  
 [73] "Lebanon"                  "Lesotho"                 
 [75] "Liberia"                  "Libya"                   
 [77] "Madagascar"               "Malawi"                  
 [79] "Malaysia"                 "Mali"                    
 [81] "Mauritania"               "Mauritius"               
 [83] "Mexico"                   "Mongolia"                
 [85] "Montenegro"               "Morocco"                 
 [87] "Mozambique"               "Myanmar"                 
 [89] "Namibia"                  "Nepal"                   
 [91] "Netherlands"              "New Zealand"             
 [93] "Nicaragua"                "Niger"                   
 [95] "Nigeria"                  "Norway"                  
 [97] "Oman"                     "Pakistan"                
 [99] "Panama"                   "Paraguay"                
[101] "Peru"                     "Philippines"             
[103] "Poland"                   "Portugal"                
[105] "Puerto Rico"              "Reunion"                 
[107] "Romania"                  "Rwanda"                  
[109] "Sao Tome and Principe"    "Saudi Arabia"            
[111] "Senegal"                  "Serbia"                  
[113] "Sierra Leone"             "Singapore"               
[115] "Slovak Republic"          "Slovenia"                
[117] "Somalia"                  "South Africa"            
[119] "Spain"                    "Sri Lanka"               
[121] "Sudan"                    "Swaziland"               
[123] "Sweden"                   "Switzerland"             
[125] "Syria"                    "Taiwan"                  
[127] "Tanzania"                 "Thailand"                
[129] "Togo"                     "Trinidad and Tobago"     
[131] "Tunisia"                  "Turkey"                  
[133] "Uganda"                   "United Kingdom"          
[135] "United States"            "Uruguay"                 
[137] "Venezuela"                "Vietnam"                 
[139] "West Bank and Gaza"       "Yemen, Rep."             
[141] "Zambia"                   "Zimbabwe"                

Afghanistan

Albania

Algeria

Angola

Argentina

Australia

Austria

Bahrain

Bangladesh

Belgium

Benin

Bolivia

Bosnia and Herzegovina

Botswana

Brazil

Bulgaria

Burkina Faso

Burundi

Cambodia

Cameroon

Canada

Central African Republic

Chad

Chile

China

Colombia

Comoros

Congo, Dem. Rep.

Congo, Rep.

Costa Rica

Cote d'Ivoire

Croatia

Cuba

Czech Republic

Denmark

Djibouti

Dominican Republic

Ecuador

Egypt

El Salvador

Equatorial Guinea

Eritrea

Ethiopia

Finland

France

Gabon

Gambia

Germany

Ghana

Greece

Guatemala

Guinea

Guinea-Bissau

Haiti

Honduras

Hong Kong, China

Hungary

Iceland

India

Indonesia

Iran

Iraq

Ireland

Israel

Italy

Jamaica

Japan

Jordan

Kenya

Korea, Dem. Rep.

Korea, Rep.

Kuwait

Lebanon

Lesotho

Liberia

Libya

Madagascar

Malawi

Malaysia

Mali

Mauritania

Mauritius

Mexico

Mongolia

Montenegro

Morocco

Mozambique

Myanmar

Namibia

Nepal

Netherlands

New Zealand

Nicaragua

Niger

Nigeria

Norway

Oman

Pakistan

Panama

Paraguay

Peru

Philippines

Poland

Portugal

Puerto Rico

Reunion

Romania

Rwanda

Sao Tome and Principe

Saudi Arabia

Senegal

Serbia

Sierra Leone

Singapore

Slovak Republic

Slovenia

Somalia

South Africa

Spain

Sri Lanka

Sudan

Swaziland

Sweden

Switzerland

Syria

Taiwan

Tanzania

Thailand

Togo

Trinidad and Tobago

Tunisia

Turkey

Uganda

United Kingdom

United States

Uruguay

Venezuela

Vietnam

West Bank and Gaza

Yemen, Rep.

Zambia

Zimbabwe

levels(gapminder$continent)

[1] "Africa"   "Americas" "Asia"     "Europe"   "Oceania" 

Africa

Americas

Asia

Europe

Oceania

Now let’s work towards dropping “Oceoania”.

We will start by filtering the gapminder data to remove observations associated with the continent of Oceania.

No_Oceania <- gapminder %>%
  filter(continent == "Africa" | continent =="Americas"|continent == "Asia"|continent == "Europe")
No_Oceania %>% 
  sample_frac(0.1) %>% #just showing a sample of the data
  knitr:: kable(format = "markdown", justify = "centre")

Let’s check how many levels there are and whether we need to remove unused factor levels.

nlevels(No_Oceania$continent)

[1] 5

levels(No_Oceania$continent)

[1] "Africa"   "Americas" "Asia"     "Europe"   "Oceania" 

Africa

Americas

Asia

Europe

Oceania

We see that there are still 5 levels. Let’s remove the unused factor levels.

Drop_Oceania <- No_Oceania %>% 
  droplevels()
nlevels(Drop_Oceania$continent)

[1] 4

levels(Drop_Oceania$continent)

[1] "Africa"   "Americas" "Asia"     "Europe"  

Africa

Americas

Asia

Europe

We do note that the factor levels are ordered alphabetically. Let’s use forcats to re-order the factor levels. We can re-order in different ways.

One way to re-order is by frequency.For example, the frequency of continents in the data.

Drop_Oceania$continent %>% 
  fct_infreq() %>% 
  levels()

[1] "Africa"   "Asia"     "Europe"   "Americas"

Africa

Asia

Europe

Americas

We can also re-order by the value of other variables in the data as life expectanc or gdp.

Drop_Oceania_1980 <- Drop_Oceania %>% 
  filter(year > 1979) %>% 
  group_by(continent, year) %>% 
  mutate(mediangdp = median(gdpPercap))

Drop_Oceania_1980

fct_reorder(Drop_Oceania_1980$continent, Drop_Oceania_1980$gdpPercap, min) %>% 
  levels() %>% head()

[1] "Africa"   "Asia"     "Americas" "Europe"  

Africa

Asia

Americas

Europe

Now we can put this into graph form.

ggplot(Drop_Oceania_1980, aes(x = year, y = Drop_Oceania_1980$mediangdp, color = fct_reorder2(continent, year, Drop_Oceania_1980$mediangdp))) +
  geom_line() +
  labs(color = "Continent")+
  xlab("Year") + ylab("Median GDP") +
  ggtitle("Median GDP 1980-2007 by Continent")

We see that reordering the levels allows the legend to be organized in the same fashion as the trendlines.

Part 2 File input and output

Let’s try saving some wrangled data into a new file.

trial<- gapminder %>%
  filter(year == "2007")

write.csv(trial, file = "assignment5_stat545")

Now let’s import this file to see if we can read it.

read.csv("assignment5_stat545")

Part 3 Visualization design

Here is an old graph from assignment 3. It looks at the weighted mean life expectancy for continents over time for the gapminder data set.

gapminder %>% 
 group_by(continent, year) %>%
 summarise(mean_lifeExp_weighted = weighted.mean(lifeExp, pop)) %>% 
 ggplot(aes(year, mean_lifeExp_weighted))+
  geom_point(aes(colour = continent))

What can be improved? 1) We can add a trend line so we can estimate what is happening between years. 2) We can change the axis titles and add a graph title. 3) We can re-order the factor levels so the legend is presented in logical order. 4) We can change the scale of the axes to show every 5 years of life. 5) We can change the graphs theme.

gapminder %>% 
 group_by(continent, year) %>%
 summarise(mean_lifeExp_weighted = weighted.mean(lifeExp, pop)) %>% 
 ggplot(aes(year, mean_lifeExp_weighted, color = fct_reorder2(continent, year, mean_lifeExp_weighted)))+
  geom_point(aes(colour = continent))+
  geom_line(aes(colour = continent))+
  scale_y_continuous(breaks=5*(1:17))+
  xlab("Year")+
    ylab("Weighted Mean Life Expectancy")+
  labs(color = "Continent")+
  ggtitle("Weighted Mean Life Expectancy vs. Time (Years)")+
  theme_minimal()

**Let’s try a different graph and also use plotly to make it more interactive.*Now we can make an interactive plot using plotly.**

Here is the original graph:

gapminder %>%
 group_by(year) %>% 
 mutate(median = median(lifeExp)) %>%
 ggplot(aes(year, lifeExp)) +
 geom_jitter(aes(colour = (lifeExp < median)), alpha = 0.5)+
  facet_wrap(~ continent)

Here is the cleaner version.

gapminder %>%
 group_by(year) %>% 
 mutate(median = median(lifeExp)) %>%
 ggplot(aes(year, lifeExp)) +
 geom_jitter(aes(colour = (lifeExp < median)), alpha = 0.5)+
  facet_wrap(~ continent,nrow = 5, ncol = 1)+
  scale_y_continuous(breaks=10*(1:9))+ #change the scale
  xlab("Year")+ #change the titles
  ylab("Life Expectancy")+
  ggtitle("Country life expectancy over time")+
  scale_colour_discrete(name  ="CountrylLife expectancy > worldwide median?")+ #make the legend clearer
  theme(legend.position="right") #select legend position

Now, let’s make this into a plotly graph.

#First, let's save the above graph into "plotly1"
plotly1 <- gapminder %>%
 group_by(year) %>% 
 mutate(median = median(lifeExp)) %>%
 ggplot(aes(year, lifeExp)) +
 geom_jitter(aes(colour = (lifeExp < median)), alpha = 0.5)+
  facet_wrap(~ continent,nrow = 5, ncol = 1)+
  scale_y_continuous(breaks=10*(1:9))+ 
  xlab("Year")+
  ylab("Life Expectancy")+
  ggtitle("Country life expectancy over time")+
  scale_colour_discrete(name  ="CountrylLife expectancy > worldwide median?")+
  theme(legend.position="right") 

#Now open plotly package.
library(plotly)

Attaching package: 'plotly'

The following object is masked from 'package:ggplot2':

    last_plot

The following object is masked from 'package:stats':

    filter

The following object is masked from 'package:graphics':

    layout

#GEnerating plotly graph.
ggplotly(plotly1)

**We do notice that plotly has some nice features. However, visualization is not as good. The legend is cut off. We can see if moving the legend elsewhere will improve this visualization.

plotly2 <- gapminder %>%
 group_by(year) %>% 
 mutate(median = median(lifeExp)) %>%
 ggplot(aes(year, lifeExp)) +
 geom_jitter(aes(colour = (lifeExp < median)), alpha = 0.5)+
  facet_wrap(~ continent,nrow = 5, ncol = 1)+
  scale_y_continuous(breaks=10*(1:9))+ 
  xlab("Year")+
  ylab("Life Expectancy")+
  ggtitle("Country life expectancy over time")+
  scale_colour_discrete(name  ="CountrylLife expectancy > worldwide median?")+
  theme(legend.position="bottom") 

#GEnerating plotly graph.
ggplotly(plotly2)

Hmmmm. It appears plotly dose not have all the aesthetic options that ggplot does. Anyways, let’s save this as a local html file.

ggplotly(plotly1) %>% 
  htmlwidgets::saveWidget("plotly1")

Let’s save this plot using ggsave(). This will generate an image file where we can specify certain aspects such as dimension and resolution.

plotly1

ggsave("plotly1.png", width = 20, height = 20, units = "cm", dpi = 300)